Scholarlink

Software-defined networks (SDNs) enable flexibility by decoupling the control and data planes, but their complex, dynamic structures challenge traditional optimization methods like rule-based algorithms and Queuing Theory (QT). To address this, we propose a framework using graph neural networks (GNNs) and deep reinforcement learning (DRL). GNNs model network components as nodes and connections as edges, learning efficient representations to improve metrics like delay, jitter, load balancing, and scalability. Our approach delivers scalable, real-time SDN optimization, significantly outperforming QT in simulations, paving the way for advanced data-driven network control.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization of Routes of SDN Using GNN and DRL

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zeeshan Mirji,
  • Muzammil Kharadi,
  • Prajwal Shiggavi,
  • Abdul Razzak R. Yergatti,
  • Mohammed Azharuddin Adhoni,
  • Suneeta V. Budihal

摘要

Software-defined networks (SDNs) enable flexibility by decoupling the control and data planes, but their complex, dynamic structures challenge traditional optimization methods like rule-based algorithms and Queuing Theory (QT). To address this, we propose a framework using graph neural networks (GNNs) and deep reinforcement learning (DRL). GNNs model network components as nodes and connections as edges, learning efficient representations to improve metrics like delay, jitter, load balancing, and scalability. Our approach delivers scalable, real-time SDN optimization, significantly outperforming QT in simulations, paving the way for advanced data-driven network control.